Give your AI agent a real Markdown workspace
Save, find, revise, review, and publish Markdown from Claude, ChatGPT, Cursor, Gemini, VS Code, or any MCP client.
Set up with one prompt
Paste it into any agent. It fetches the instructions and installs itself.
Fetch and follow the appropriate instructions to connect this agent to mdedit.ai from https://mdedit.ai/agent-setup/prompt.md
By Vivek Maskara · Last updated
What you'd ask for
Four prompts you can paste into a connected client, and what each one does to your document.
Review this draft and leave suggestions instead of editing directly.
Summarize the open review threads and resolve the ones I already replied to.
Create a document from these meeting notes in my Docs workspace.
Publish this doc as a live link.
Install for your host
The same plugin, version 0.3.2, installs in every host below. Each one handles its own sign-in.
Or paste the setup prompt and let the agent install itself.
ChatGPT and Codex
AvailableInstall Markdown by mdedit.ai from the ChatGPT Store.
codex mcp add mdedit --url https://mcp.mdedit.ai/mcp
codex mcp login mdedit
Claude Code
Available from sourceAdd the MCP connection with one command, or load the plugin from the shared repository.
claude mcp add --transport stdio mdedit -- npx -y @mdedit/mcp-server
The plugin is ready and awaiting marketplace listing. Until then, load it from the shared repository or use CLI-backed skills.
Cursor and VS Code
Available from sourceIn VS Code, run Chat: Install Plugin From Source with the repository URL. In Cursor, install the same repository from source.
Add to CursorOne click adds the MCP connection with browser sign-in. The five skills come with the plugin install above.
The plugin is ready and awaiting marketplace listing. Until then, install the shared repository from source.
Gemini CLI
Available from sourceInstall the extension with the repository URL, then authenticate when prompted.
gemini extensions install \ https://github.com/mdedit-ai/mdedit-agent-plugin
The extension is ready and awaiting gallery listing. Until then, install it with the repository URL.
Any MCP client
Add the hosted server URL in your client's MCP settings and sign in when prompted.
Connect a custom MCP clienthttps://mcp.mdedit.ai/mcpSkills-only installs and every host's details are in Install mdedit agent skills.
The agent proposes, you approve
Suggestions wait for a person
An agent proposal stays anchored to its passage until you accept or reject it in the editor.
Publishing asks first
A public link needs the publishing:write scope and an explicit confirmation on the tool call.
Nothing beyond the grant
Every action is limited to what the key or the sign-in allows, and anything else fails closed.
The five skills tell the agent when to save, find, revise, review, or publish, so it reaches for the right tool at the right moment. Read the skill catalog.
You
Review my launch brief and leave suggestions for anything unclear.
Agent
3 suggestions added, nothing changed in your text.
Suggestion 1 of 3
We plan to ship the update soon to most customers.
The update reaches every paid workspace on 14 October.
Connect a custom MCP client
Connect with browser sign-in
https://mcp.mdedit.ai/mcpAdd the server URL in your client, sign in to mdedit.ai, and approve workspace access. You can narrow the selected workspaces or choose read-only access before connecting. Clients that browse the official MCP registry can find the server as io.github.mangoappstudio/mdedit.
API keys for automation
For clients without browser sign-in or unattended workflows, create a scoped key in Settings, Integrations, API Keys.
claude mcp add --transport stdio \ --env MDEDIT_API_KEY=mdh_your_key \ mdedit -- npx -y @mdedit/mcp-server
Already use the mdedit.ai CLI?
Run mdedit auth login once and the local MCP server picks up that sign-in from your operating system keychain, so nothing secret goes into your client config. Node.js 20 or newer is required for the local package.
Client by client setup lives in the Claude Code guide, and connection troubleshooting in MCP authentication.
Tools at a glance
Read and explore
4 toolsFind the right workspace and open a document before touching anything.
Write, review and suggest
9 toolsDraft, propose, and work through feedback where your team already reads it.
Export and convert
4 toolsTurn a document into Markdown, HTML, PDF, DOCX or a Zip bundle, and bring outside files in.
Publish and presence
5 toolsPublic links stay behind a confirmation, and agents appear alongside your teammates.
Twenty-two tools total. Full list in the agent docs.
One key per agent, scoped to one job
Keys start with mdh_ and carry a fixed set of permissions.
Review only
articles:read, reviews:writeReads documents and leaves comments and suggestions. It cannot rewrite your prose.
Editor
articles:writeCreates documents and applies anchored edits. A write scope also covers the matching read.
Publisher
publishing:writeCreates or disables a public mded.it link, and only with the confirmation flag set.
A tool the key cannot reach returns a permission challenge instead of doing half the work. Read the API key guide.
Other ways to automate mdedit.ai
Command line
Script workspaces, documents, and exports from your terminal, with JSON output for pipelines.
See the CLIWebhooks
Wake your own process when a reviewer mentions an agent or a document changes.
Read the webhook guideAgent plugin FAQs
One plugin, in the Agent Plugins 1.0 format. It bundles the hosted mdedit MCP connection with five skills: Save, Find, Revise, Review, and Publish. The same package carries thin host adapters for Claude Code, Cursor, and Gemini CLI, and the plugin is listed in the ChatGPT Store as Markdown by mdedit.ai. See installation by host.
The Model Context Protocol is an open standard for connecting AI clients to external tools. An MCP server publishes a list of typed tools, and the client decides which ones to call. @mdedit/mcp-server is the mdedit.ai implementation, and it publishes twenty-two tools for Markdown documents.
Yes. In clients that support browser sign-in, connect to https://mcp.mdedit.ai/mcp, sign in to mdedit.ai, and approve workspace access. All available workspaces are selected by default; you can narrow access before connecting. The local MCP package can also use your CLI sign-in. API keys are optional for clients without browser sign-in and for automation. See MCP authentication.
Clients that support remote MCP and browser sign-in can connect to the hosted endpoint. The agent plugin includes installation options for VS Code, Gemini CLI, Cursor, and Claude Code. Clients that launch local MCP processes can use the npm package with a shared CLI sign-in or an API key. See the installation guide for your client.
Use https://mcp.mdedit.ai/mcp and browser sign-in when your client supports remote MCP. Use the local package when your client launches MCP processes. Both paths provide the document tools; API keys are optional for automation and clients without browser sign-in. See MCP authentication.
No. Publishing needs the publishing:write scope, and publish_article also needs an explicit confirmation flag on the call. An ordinary editing key cannot make a document public. Once a link exists, anyone who has it can read the document, so treat that step as a deliberate one.
The call fails closed. The tool returns a permission challenge naming the missing scope instead of partially completing the work, so a review-only key stays review-only.
No. add_suggestion records a proposed replacement against a passage, and it stays a proposal until a person accepts it in the editor. add_comment never changes prose at all. Only edit_article writes to the document, and it needs a grant scoped for writing.
They serve different jobs, and they share one sign-in. MCP is for an agent working inside a document during a session. The mdedit.ai CLI is for scripts, pipelines, and terminal work where you want plain commands and JSON output.
Give your agent a document to work in
Install the plugin for your host, and keep the final say on every change.